Telefonaktiebolaget Lm Ericsson (publ)

Martha Vlachou-Konchylaki

Yu Wang

Vincent Huang

Swarup Kumar Mohalik

Efthymios Stathakis

Tobias Ley

Arthur Gusmao

Joerg Niemoeller

Wenfeng Hu

Roberta Daidone

Jörg Niemöller

Wei Huang

A method of configuration in a communications network includes: obtaining operational data relating to operation of at least one network node, the operational data including, for each of a plurality of time periods, data relating to at least one configuration parameter of the network node and data relating to at least one performance indicator of the network node; defining a plurality of actions, wherein each action corresponds to a specific set of values of the at least one configuration parameter in two successive time periods; and defining a plurality of states, wherein each state corresponds to one specific set of values of the operational data. A probabilistic graph is constructed from the operational data, the probabilistic graph indicating, for a plurality of the defined states, a probability that an action will lead to a transition to a respective other state.

Configuration of a communications network

The properties of a plurality of operational units are estimated by generating a central system state graph model representing the properties of the plurality of operational units as probabilities of transitions between states for the plurality of operational units, where the states represent operational data. Then a respective updated system state graph model is generated for each of the plurality of operational units, based on the central system state graph model and based on new operational data for the respective operational unit. A distance measure is determined between the respective updated system state graph models. If the distance measure fulfils a divergence criterion, a plurality of new central system state graph models are generated, each representing the properties of a respective subset of the plurality of operational units as the probabilities of transitions between states for the respective subset of the plurality of operational units.

Estimating properties of units using system state graph models

A pre-training apparatus and method for reinforcement learning based on a Generative Adversarial Network (GAN) is provided. GAN includes a generator and a discriminator. The method comprising receiving training data from a real environment where the training data includes a data slice corresponding to a first state-reward pair and a first state-action pair, training the GAN using the training data, training a relations network to extract a latent relationship of the first state-action pair with the first state-reward pair in a reinforcement learning context, causing the generator trained with training data to generate first synthetic data, processing a portion of the first synthetic data in the relations network to generate a resulting data slice, merging the second state-action pair portion of the first synthetic data with the second state-reward pair from the relations network to generate second synthetic data to update a policy for interaction with the real environment.

Pre-training system for self-learning agent in virtualized environment

A method for training a Software Agent to control a communication network is disclosed. The method comprises initialising a training network slice within the communication network, instantiating within the training network slice a cloned version of at least one Virtualised Network Function (VNF) comprised within a production network slice, mirroring traffic incoming to the VNFs of the production network slice and forwarding the mirrored traffic to the training network slice. The method further comprises causing a training instance of the Software Agent to execute a Reinforcement Learning algorithm on the training network slice, and transferring knowledge acquired by the training instance of the Software Agent to a production instance of the Software Agent. Also disclosed are an apparatus and a computer program configured to carry out methods for training a Software Agent to control a communication network.

Training a software agent to control a communication network

A method () of enabling improved efficiency in a first communications network (A) based on relation metrics on a relation between a first operator (A) of the first communications network (A) and a second operator (B) of a second communications network (A,B). The method () is performed in a network entity () and comprises: obtaining () data relating to users having a subscription with the first operator (A) and data relating to users having a subscription with the second operator (B); determining (), based on the obtained data relating to users, a first metric IAB giving number of users roaming to the first operator (A) from the second operator (B) and a second metric OAB giving number of users roaming from the first operator (A) to the second operator (B); and providing () the first and second metrics IAB, OAB as relation metrics to a network device (A) of the first communications network (A) for use in improving efficiency in the first communications network (A). A method () in a network device (A) is also provided, and a network entity, a network device, computer programs and computer program products.

Method of enabling improved efficiency in a first communications network, network entity, network device, computer programs and computer program products

Growing community of inventors

Stockholm, Sweden

Martha Vlachou-Konchylaki